mps-run-configurations

Create and execute IDE run configurations for MPS root nodes via MPS MCP — Java Application for `IMainClass` / `ClassConcept` with `main`, JUnit Tests for `ITestCase`. Use when launching DSL `main`-like roots, plain BaseLanguage `ClassConcept` mains, or MPS test cases from a node; reusing or replacing an existing run config; diagnosing `ClassNotFoundException`, `compileInMPS=false`, or "not runnable through this tool" failures.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-organized, action-oriented overview with clear directives, a sequenced workflow, and an exemplary reference index — but it references six files in references/ that are not present in the bundle, breaking the progressive-disclosure navigation it advertises.

Suggestions

Ship the six referenced files (runnable-shapes.md, create-and-execute.md, classconcept-and-fallbacks.md, compile-before-run.md, decision-matrix.md, common-failures.md) under references/ so the Reference Index links resolve.

Add an explicit validation checkpoint in the Common Workflow (e.g., confirm the MAKE reached classes_gen before executing the run config) rather than only recovering after a launch failure.

Tighten the opening paragraph and remove 'the goal is' / explanatory asides to lift conciseness toward fully lean.

Dimension	Reasoning	Score
Conciseness	Mostly lean and action-oriented with domain-specific directives that assume Claude's competence, though the opening orientation paragraph and a few 'the goal is' phrasings could be trimmed without losing clarity.	4 / 5
Actionability	The Common Workflow gives concrete tool calls with parameters (mps_mcp_alter_nodes MAKE with rebuild:true, execute_run_configuration with waitForExit:true and timeout), but stops short of copy-paste-ready code blocks covering common cases.	4 / 5
Workflow Clarity	A clear 4-step numbered sequence with an error-recovery feedback loop in step 4 (re-run MAKE on 'Could not find or load main class'), though an explicit 'verify build reached classes_gen before running' checkpoint is only implied.	4 / 5
Progressive Disclosure	The Reference Index is well-signaled and one-level-deep with purpose-driven 'Open X when...' navigation, but the six referenced files under references/ do not exist in the bundle, so the disclosure structure points to material that is missing and navigation would fail.	3 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities, runnable shapes, and trigger conditions while naming concrete failure modes users would encounter. It avoids fluff and is clearly distinguishable from neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (create and execute run configurations) with three explicit runnable shapes (IMainClass, ITestCase, ClassConcept with main), giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what (create/execute IDE run configurations for MPS root nodes via MPS MCP, with three shapes) and when (Use when launching..., reusing/replacing, diagnosing specific failures) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrases ('launching DSL main-like roots', 'MPS test cases', 'run config') plus concrete error strings (ClassNotFoundException, compileInMPS=false, 'not runnable through this tool') that users would actually report.	5 / 5
Distinctiveness Conflict Risk	Targets a narrow, well-scoped niche (MPS root nodes via MPS MCP) with distinct triggers and explicit non-goals (not launching MPS itself), minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-run-configurations/SKILL.md
Commit: 1f2bdbb

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.